This paper presents GHOST, a combinatorial optimization framework that a Real-Time Strategy (RTS) AI developer can use to model and solve any problem encoded as a constraint satisfaction/optimization problem. We show a way to model three different problems as a constraint satisfaction/optimization problem, using instances from the RTS game StarCraft as test beds. Each problem belongs to a specific level of abstraction (the target selection as reactive control problem, the wall-in as a tactics problem and the build order planning as a strategy problem). In our experiments, GHOST shows good results computed within some tens of milliseconds. We also show that GHOST outperforms state-of-the-art constraint solvers, matching them on the resources allocation problem, a common combinatorial optimization problem. is with the JST-ERATO Kawarabayashi Large Graph project at the National Institue of Informatics, Japan.CSP/COP offers a convenient, homogeneous framework that is able to model a large number of combinatorial optimization problems, and proposes various sets of algorithms to solve them.CSP/COP is widely used in AI to solve problems such us pathfinding, scheduling, and logistics [6]. Unlike Mathematical Programming, CSP/COP algorithms are not usually designed to solve one specific problem but are general, i.e., they are able to manage any problem modeled in that framework. Besides the generality, it is also easy and intuitive to model a problem with a CSP/COP. Altogether, these bring ideal conditions to design and develop a user-friendly, easy-to-extend and generalized solver. A. RTS problem familiesOntañón et al. propose in [1] to decompose RTS problems into three families, according to their level of abstraction. From the higher to the lower level, these families are:• Strategy corresponds to the high-level decision making process. This is the highest level of abstraction for game comprehension. Finding an efficient strategy or counterstrategy against a given opponent is key in RTS games. It concerns the whole set of units and buildings a player owns. • Tactics are the implementation of the current strategy.It implies army and building positioning, movements, timing, and so on. Tactics concerns a group of units. • Reactive control is the implementation of tactics. This consists in moving, targeting, firing, fleeing, hit-andrun techniques (also knows as "kiting") during battle. Reactive control focuses on a specific unit.Problems from different families usually involve different algorithms to solve them. In this paper, we model one problem for each of these three families. Then we use our framework GHOST to solve them without any modifications of its inner solver. B. StarCraft: Brood WarStarCraft: Brood War is an RTS game where three different races (Terran, Protoss and Zerg) can be played, giving an asymmetric but well balanced strategy game. In this paper, the term "StarCraft" will actually refer to the game plus its expansion StarCraft: Brood War.StarCraft has been a worldwide success, and as of time of publicat...

Knowledge is created and transmitted through generations, and innovation is often seen as a process generated from collective intelligence. There is rising interest in studying how innovation emerges from the blending of accumulated knowledge, and from which path an innovation mostly inherits. A citation network can be seen as a perfect example of one generative process leading to innovation. However, the impact and influence of scientific publication are always difficult to capture and measure. We offer a new take on investigating how the knowledge circulates and is transmitted, inspired by the notion of “stream of knowledge”. We propose to look at this question under the lens of flows in directed acyclic graphs (DAGs). In this framework inspired by the work of Strahler, we can also account for other well known measures of influence such as the h-index. We propose then to analyze flows of influence in a citation networks as an ascending flow. From this point on, we can take a finer look at the diffusion of knowledge through the lens of a multiplex network. In this network, each citation of a specific work constitutes one layer of interaction. Within our framework, we design three measures of multiplex flows in DAGs, namely the aggregated, sum and selective flow, to better understand how citations are influenced. We conduct our experiments with the arXiv HEP-Th dataset, and find insights through the visualization of these multiplex networks.

Knowledge is created and transmitted through generation. Innovation is often seen as a generative process from collective intelligence, but how does innovation emerges from the blending of accumulated knowledge, and from which path an innovation mostly inherit? A citation network can be seen as a perfect example of a generative process leading to innovation. Inspired by the notion of "stream of knowledge", we propose to look at the question of production of knowledge under the lens of DAGs. Although many works look for the evaluation of publications, we propose to look for production of knowledge within a framework for analyzing DAGs. In this framework inspired by the work of Strahler, we can also account for other well known measures of influence such as the h-index. We propose then to analyze flows of influence in a citation networks as an ascending flow. We propose an efficient dynamic algorithm for integration with modern graph databases, conducting our experiment with the Arxiv HEP-TH dataset. Our results validate the use of DAG flows for citation flows and show evidence of the relevance of the h-index.